跳到主要导航 跳到搜索 跳到主要内容

Implementation and Verification of a Virtual Testing System Based on ROS and Unity for Computer Vision Algorithms

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

With the development of artificial intelligence technology, Computer vision algorithm is playing an increasingly important role. Computer vision algorithm testing is a vital link to ensure the safe and reliable operation of agents. However, the traditional testing methods based on real scenes provide single samples and are challenging to obtain ground truth, which makes it inefficient to test computer vision algorithms. To solve this problem, the testing method of computer vision algorithms using virtual scenes instead of real scenes has been applied. In this paper, Unity and robot operating system (ROS) are selected to build a virtual testing system named URCV for computer vision algorithms. The feasibility of the system and the influence of virtual scene elements on the testing of the monocular ORB-SLAM2 algorithm are verified, including the rendering path of Unity's RGB camera, texture accuracy, and illumination model.

源语言英语
主期刊名Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
编辑Qingli Li, Lipo Wang
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781728148526
DOI
出版状态已出版 - 10月 2019
活动12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019 - Huaqiao, 中国
期限: 19 10月 201921 10月 2019

出版系列

姓名Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

会议

会议12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
国家/地区中国
Huaqiao
时期19/10/1921/10/19

指纹

探究 'Implementation and Verification of a Virtual Testing System Based on ROS and Unity for Computer Vision Algorithms' 的科研主题。它们共同构成独一无二的指纹。

引用此